University of Colorado Data Center Scale Computing
Abstract
This project is for students enrolled in CSCI 4830 & 7000 in Fall 2014 at the University of Colorado. Students learn about "data center scale" computing, meaning large scale distributed systems suitable for data-centric (rather than purely computational) computing. Using VM resources students will use Hadoop, Spark and related resources and also build a distributed application.
Intellectual Merit
This project (and related course) are designed to teach a new generation of computer science undergraduate & graduate students about distributed systems, cloud computing and data-centric computing. Students are not expected to produce new research (although they are required to complete a project).
Broader Impact
This project (and related course) are designed to teach a new generation of computer science undergraduate & graduate students about distributed systems, cloud computing and data-centric computing. The class serves 20 undergraduate students and about 25 graduate students.
Use of FutureGrid
Students will use FutureGrid to develop a distributed application as part of the course and also to develop their own projects for the course.
Scale Of Use
Students will need to use a few VM's, primarily during the middle of the semester.